© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2569
    Prev
    Next
    INDEX
    Explanations

    governors and state elections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rikt
    -0.73
     intraven
    -0.73
     hollywood
    -0.72
     명
    -0.72
     přid
    -0.72
    hage
    -0.71
    Dislikes
    -0.70
     navigator
    -0.70
    Designing
    -0.70
     március
    -0.69
    POSITIVE LOGITS
     Virginia
    1.27
     off
    1.09
    Virginia
    1.05
     governors
    1.00
     governor
    0.94
     Governors
    0.92
     Nj
    0.87
     couvert
    0.84
    off
    0.81
     candidate
    0.81
    Activations Density 0.061%

    No Known Activations